In this video from ISC 2019, Dan Bounds from AMD describes how the company is powering a new generation of supercomputers with their EPYC processors and Radeon Instinct GPUs.
Truly accelerating the pace of deep learning and addressing the broad needs of the datacenter requires a combination of high performance compute and GPU acceleration optimized for handling massive amounts of data with heaps of floating-point computation that can be spread across many cores. Large system designers today also need efficient systems with the flexibility and openness to meet the challenge of demanding workloads. AMD is raising the bar on compute densities by enabling optimized server designs with high performance, low latency, and excellent efficiency in an open, flexible environment. With the introduction of new EPYC processor-based servers with Radeon Instinct GPU accelerators, combined with our ROCm open software ecosystem, AMD is ushering in a new era of heterogeneous compute for HPC and Deep Learning.
Powered by AMD, the Frontier supercomputer coming to ORNL is expected to be World’s Fastest Supercomputer in 2021. To enable exascale-class scientific research,AMD in collaboration with the U.S. Department of Energy, Oak Ridge National Laboratory, and Cray Inc., will create the Frontier system with a whopping 1.5 exaflops of peak processing power.